The most common RAG systems rely on a frozen RAG system — one where there’s a single embedding model and single vector index. We’ve achieved a modicum of success with that, but when it comes to increasing accuracy for production systems there is only so much this approach solves. In this session we will explore how to move from the frozen systems to adaptive RAG systems which produce more tailored outputs with higher accuracy. Databricks services: Lakehouse, Unity Catalog, Mosaic, Sweeps, Vector Search, Agent Evaluation, Managed Evaluation, Inference Tables